A statistical model of Riemannian metric variation for deformable shape analysis

The analysis of deformable 3D shape is often cast in terms of the shape's intrinsic geometry due to its invariance to a wide range of non-rigid deformations. However, object's plasticity in non-rigid transformation often result in transformations that are not completely isometric in the surface's geometry and whose mode of deviation from isometry is an identifiable characteristic of the shape and its deformation modes. In this paper, we propose a novel generative model of the variations of the intrinsic metric of deformable shapes, based on the spectral decomposition of the Laplace-Beltrami operator. To this end, we assume two independent models for the eigenvectors and the eigenvalues of the graph-Laplacian of a 3D mesh which are learned in a supervised way from a set of shapes belonging to the same class. We show how this model can be efficiently learned given a set of 3D meshes, and evaluate the performance of the resulting generative model in shape classification and retrieval tasks. Comparison with state-of-the-art solutions for these problems confirm the validity of the approach.

[1]  Iasonas Kokkinos,et al.  Scale-invariant heat kernel signatures for non-rigid shape recognition , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[2]  Niklas Peinecke,et al.  Laplace-spectra as fingerprints for shape matching , 2005, SPM '05.

[3]  Daniel Cremers,et al.  The wave kernel signature: A quantum mechanical approach to shape analysis , 2011, 2011 IEEE International Conference on Computer Vision Workshops (ICCV Workshops).

[4]  A. Ben Hamza,et al.  Skeleton Path Based Approach for Nonrigid 3D Shape Analysis and Retrieval , 2011, IWCIA.

[5]  Szymon Rusinkiewicz,et al.  Rotation Invariant Spherical Harmonic Representation of 3D Shape Descriptors , 2003, Symposium on Geometry Processing.

[6]  A. Ben Hamza,et al.  Intrinsic spatial pyramid matching for deformable 3D shape retrieval , 2013, International Journal of Multimedia Information Retrieval.

[7]  Leonidas J. Guibas,et al.  A concise and provably informative multi-scale signature based on heat diffusion , 2009 .

[8]  Thomas A. Funkhouser,et al.  The Princeton Shape Benchmark , 2004, Proceedings Shape Modeling Applications, 2004..

[9]  Yizhou Yu,et al.  Fast nonrigid 3D retrieval using modal space transform , 2013, ICMR.

[10]  Thomas Hofmann,et al.  Unsupervised Learning by Probabilistic Latent Semantic Analysis , 2004, Machine Learning.

[11]  Mikhail Belkin,et al.  Discrete laplace operator on meshed surfaces , 2008, SCG '08.

[12]  Michael G. Strintzis,et al.  3D object retrieval using the 3D shape impact descriptor , 2009, Pattern Recognit..

[13]  Guillaume Lavoué,et al.  Combination of bag-of-words descriptors for robust partial shape retrieval , 2012, The Visual Computer.

[14]  Niklas Peinecke,et al.  Laplace-Beltrami spectra as 'Shape-DNA' of surfaces and solids , 2006, Comput. Aided Des..

[15]  Hao Zhang,et al.  A spectral approach to shape-based retrieval of articulated 3D models , 2007, Comput. Aided Des..

[16]  Raif M. Rustamov,et al.  Laplace-Beltrami eigenfunctions for deformation invariant shape representation , 2007 .

[17]  Xiaogang Wang,et al.  Learning Semantic Signatures for 3D Object Retrieval , 2013, IEEE Transactions on Multimedia.

[18]  Cordelia Schmid,et al.  Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[19]  Alexander M. Bronstein,et al.  Supervised learning of bag‐of‐features shape descriptors using sparse coding , 2014, Comput. Graph. Forum.

[20]  Mohamed Daoudi,et al.  Indexed heat curves for 3D-model retrieval , 2012, Proceedings of the 21st International Conference on Pattern Recognition (ICPR2012).

[21]  Andrea Giachetti,et al.  Radial Symmetry Detection and Shape Characterization with the Multiscale Area Projection Transform , 2012, Comput. Graph. Forum.

[22]  Alberto Del Bimbo,et al.  Content-based retrieval of 3D models , 2006, TOMCCAP.

[23]  Alexander M. Bronstein,et al.  Numerical Geometry of Non-Rigid Shapes , 2009, Monographs in Computer Science.

[24]  Yosi Keller,et al.  Scale-Invariant Features for 3-D Mesh Models , 2012, IEEE Transactions on Image Processing.

[25]  Leonidas J. Guibas,et al.  Fine-grained semi-supervised labeling of large shape collections , 2013, ACM Trans. Graph..

[26]  François Bourgeois,et al.  An extension of the Munkres algorithm for the assignment problem to rectangular matrices , 1971, CACM.

[27]  Leonidas J. Guibas,et al.  Shape google: Geometric words and expressions for invariant shape retrieval , 2011, TOGS.

[28]  Trevor Darrell,et al.  The pyramid match kernel: discriminative classification with sets of image features , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[29]  Chang-Hsing Lee,et al.  A new 3D model retrieval approach based on the elevation descriptor , 2007, Pattern Recognit..

[30]  Remco C. Veltkamp,et al.  A Survey of Content Based 3D Shape Retrieval Methods , 2004, SMI.

[31]  Sebastian Thrun,et al.  SCAPE: shape completion and animation of people , 2005, SIGGRAPH 2005.

[32]  Sven J. Dickinson,et al.  From skeletons to bone graphs: Medial abstraction for object recognition , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[33]  Saturnino Maldonado-Bascón,et al.  Evaluating 3D spatial pyramids for classifying 3D shapes , 2013, Comput. Graph..

[34]  Daniel Cremers,et al.  Dense Non-rigid Shape Correspondence Using Random Forests , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[35]  D. Kendall.  SHAPE MANIFOLDS, PROCRUSTEAN METRICS, AND COMPLEX PROJECTIVE SPACES , 1984 .

[36]  Bernard Chazelle,et al.  Shape distributions , 2002, TOGS.

[37]  Michael I. Jordan,et al.  Latent Dirichlet Allocation , 2001, J. Mach. Learn. Res..

[38]  P. Schönemann,et al.  A generalized solution of the orthogonal procrustes problem , 1966 .

[39]  Thomas A. Funkhouser,et al.  Shape-based retrieval and analysis of 3d models , 2005, CACM.

[40]  Andrea Fusiello,et al.  The bag of words approach for retrieval and categorization of 3D objects , 2010, The Visual Computer.

[41]  Jovan Popović,et al.  Deformation transfer for triangle meshes , 2004, SIGGRAPH 2004.

[42]  Bo Li,et al.  Shape Retrieval of Non-Rigid 3D Human Models , 2014, 3DOR@Eurographics.

[43]  Andrea Torsello,et al.  A Non-cooperative Game for 3D Object Recognition in Cluttered Scenes , 2011, 2011 International Conference on 3D Imaging, Modeling, Processing, Visualization and Transmission.

[44]  A. Ben Hamza,et al.  Reeb graph path dissimilarity for 3D object matching and retrieval , 2011, The Visual Computer.

[45]  Yang Yu.  Content-Based 3D Model Retrieval: A Survey , 2004 .

[46]  A. Ben Hamza,et al.  A multiresolution descriptor for deformable 3D shape retrieval , 2013, The Visual Computer.